INDEX

Explanations

code elements and programming-related terms

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

utow

-0.16

].[

-0.15

Ð¾Ð²Ð°ÑĢÐ¸

-0.14

arro

-0.14

Ð¾Ð²Ð°ÑĢ

-0.14

/INFO

-0.13

nothrow

-0.13

();↵

-0.13

stras

-0.13

 Exception

-0.13

POSITIVE LOGITS

.go

0.23

pkg

0.20

util

0.20

htt

0.19

pb

0.19

spb

0.19

 structs

0.18

nil

0.18

pkg

0.18

itempty

0.18

Activations Density 0.012%

code elements and programming-related terms

No Comments

No Known Activations